Dynamic trajectory planning method for performing obstacle avoidance and overtaking based on lane line parallel shift

Abstract

The invention relates to a dynamic trajectory planning method for performing obstacle avoidance and overtaking based on lane line parallel shift. Different state spaces are established for different road scenes, so that trajectory planning under different working conditions is achieved; and a more accurate subsequent real-time trajectory is planned through coordinate conversion and decoupling. Themethod has the beneficial effects that the different state spaces are established for the different road scenes, so that the effective and accurate trajectory planning under the different working conditions is achieved; through the coordinate conversion and decoupling, the more accurate real-time trajectory planning is achieved for a subsequent trajectory planning party; a planned trajectory screening objective function and constraint conditions are set, so that the trajectory planning efficiency is improved, and the safety, comfort and stability requirements of trajectory planning are met; and evaluation conditions for ensuring the path consistency are set, so that the situation that unsafe factors are generated for a planned path due to environmental changes during vehicle running is avoided, and a dangerous warning of the planned path can be found in time to carry out trajectory re-planning or a driver can be reminded to carry out intervention operation when an optimal path cannotbe selected.

Description

technical field [0001] The invention belongs to the technical field of unmanned vehicles, and in particular relates to a dynamic trajectory planning method for obstacle avoidance and overtaking based on parallel offset of lane lines. Background technique [0002] With the rapid growth of car ownership, the problems caused by cars are becoming more and more obvious, and traffic safety problems are becoming more and more prominent. The main reasons for traffic accidents are weather, road defects, car failures, and improper driver operations. Development can effectively solve safety problems and make up for traffic accidents caused by human factors. [0003] The trajectory planning method of unmanned vehicles can plan effective driving trajectories on the basis of vehicle-road coordination, so as to realize the functions of obstacle avoidance and overtaking during vehicle driving, thereby greatly reducing the accidents caused by driver's misjudgment and misoperation. traffic a...

AI Technical Summary

Problems solved by technology

[0004] In the prior art, the reference trajectory of local path planning is offset in parallel, so that the path after parallel offset can bypass obstacles. There are the following technical difficulties: 1. Due to the curvature in the road, the unmanned vehicle travels to a parallel offset. The smooth connection path between the moving paths is difficult to plan; 2. Since the position of the unmanned vehicle is not parallel to the path tangent vector, it is difficult to plan the smooth connection path between the unmanned vehicle and the parallel offset path; 3. When generating On the basis of the path, it is difficult to carry out smooth speed planning and acceleration planning, so it is difficult to meet the comfort requirements; 4. When the parallel offset path follows the real-time changes of the environment, it is difficult to ensure the consistency of the path planning and cannot meet the stability requirements; 5. Existing technologies are not suitable for unmanned driving trajectory planning on structured roads

Images